Providers/Novita AI

Novita AI

Cloud platform · novita.ai

Novita AI models via API.

Models

85

Endpoints

5

Regions

0

Avg input

$0.31

Auth

API key

SDKs

0

Endpoints

POST/v1/chat/completionsCompletionsStream

POST/v1/embeddingsEmbeddings-

POST/v1/messagesMessagesStream

POST/v1/rerankRerank-

POST/v1/responsesResponsesStream

Models · 85

ModelContextInputOutputCapabilities

minimax-m2.1Open205K$0.30$1.20ToolsJSON glm-4.7Open205K$0.60$2.20ReasoningToolsJSON glm-4.6vOpen131K$0.30$0.90ReasoningVisionTools deepseek-v3.2Open164K$0.27$0.40ReasoningToolsJSON kimi-k2-thinkingOpen262K$0.60$2.50ReasoningToolsJSON minimax-m2Open205K$0.30$1.20ReasoningTools qwen3-vl-8b-instructOpen131K$0.08$0.50VisionToolsJSON qwen3-vl-30b-a3b-instructOpen131K$0.20$0.70VisionToolsJSON qwen3-vl-30b-a3b-thinkingOpen131K$0.20$1.00VisionToolsJSON glm-4.6Open205K$0.55$2.20ReasoningToolsJSON deepseek-v3.2-expOpen164K$0.27$0.41ReasoningToolsJSON qwen3-maxOpen262K$2.11$8.45ToolsJSON qwen3-vl-235b-a22b-instructOpen131K$0.30$1.50VisionToolsJSON qwen3-vl-235b-a22b-thinkingOpen131K$0.98$3.95ReasoningVision deepseek-v3.1-terminusOpen131K$0.27$1.00ReasoningToolsJSON qwen3-next-80b-a3b-instructOpen131K$0.15$1.50ToolsJSON qwen3-next-80b-a3b-thinkingOpen131K$0.15$1.50ReasoningToolsJSON kimi-k2-0905Open262K$0.60$2.50ToolsJSON glm-4.5vOpen66K$0.60$1.80ReasoningVisionTools gpt-oss-120bOpen131K$0.05$0.25ReasoningVisionTools gpt-oss-20bOpen131K$0.04$0.15ReasoningVisionTools qwen3-coder-30b-a3b-instructOpen160K$0.07$0.27ToolsJSON glm-4.5Open131K$0.60$2.20ReasoningTools glm-4.5-airOpen131K$0.13$0.85ReasoningTools qwen3-235b-a22b-thinking-2507Open131K$0.30$3.00ReasoningTools ernie-4.5-vl-424b-a47bOpen123K$0.42$1.25ReasoningVision deepseek-r1-0528Open164K$0.70$2.50ReasoningToolsJSON llama-4-scout-17b-16e-instructOpen131K$0.18$0.59Vision gemma-3-12b-itOpen131K$0.05$0.10VisionToolsJSON gemma-3-27b-itOpen98K$0.12$0.20Vision qwen2.5-vl-72b-instructOpen33K$0.80$0.80Vision deepseek-r1-distill-llama-70bOpen8K$0.80$0.80ReasoningToolsJSON llama-3.3-70b-instructOpen131K$0.14$0.40Tools qwen2.5-7b-instructOpen32K$0.07$0.07ToolsJSON llama-3.2-3b-instructOpen33K$0.03$0.05Tools qwen-2.5-72b-instructOpen32K$0.38$0.40ToolsJSON llama-3.1-8b-instructOpen16K$0.02$0.05 mistral-nemoOpen60K$0.04$0.17ToolsJSON wizardlm-2-8x22b66K$0.62$0.62 mythomax-l2-13bOpen4K$0.09$0.09 L3-8B-Stheno-v3.28K$0.05$0.05Tools autoglm-phone-9b-multilingual66K$0.04$0.14Vision baichuan-m2-32b131K$0.07$0.07 bge-m38K$0.01$0.01Embeddings bge-reranker-v2-m38K$0.01$0.01 deepseek-ocrOpen8K$0.03$0.03VisionToolsJSON deepseek-prover-v2-671bOpen160K$0.70$2.50 deepseek-r1-0528-qwen3-8bOpen128K$0.06$0.09Reasoning deepseek-r1-distill-qwen-14bOpen33K$0.15$0.15ReasoningToolsJSON deepseek-r1-distill-qwen-32bOpen64K$0.30$0.30ReasoningToolsJSON deepseek-r1-turboOpen64K$0.70$2.50ReasoningTools deepseek-v3-0324Open164K$0.27$1.12ToolsJSON deepseek-v3-turboOpen64K$0.40$1.30Tools deepseek-v3.1Open131K$0.27$1.00ReasoningToolsJSON ernie-4.5-21B-a3b120K$0.07$0.28Tools ernie-4.5-21B-a3b-thinking131K$0.07$0.28Reasoning ernie-4.5-300b-a47b-paddle123K$0.28$1.10ToolsJSON ernie-4.5-vl-28b-a3b30K$0.14$0.56ReasoningVisionTools ernie-4.5-vl-28b-a3b-thinking131K$0.39$0.39ReasoningVisionTools hermes-2-pro-llama-3-8bOpen8K$0.14$0.14ToolsJSON kat-coder-pro256K$0.30$1.20ToolsJSON kimi-k2-instructOpen131K$0.57$2.30ToolsJSON l3-70b-euryale-v2.18K$1.48$1.48Tools l3-8b-lunaris8K$0.05$0.05ToolsJSON l31-70b-euryale-v2.28K$1.48$1.48Tools llama-3-70b-instructOpen8K$0.51$0.74ToolsJSON llama-3-8b-instructOpen8K$0.04$0.04 llama-4-maverick-17b-128e-instruct-fp8Open1.0M$0.27$0.85Vision mimo-v2-flash262K$0.10$0.30ReasoningToolsJSON minimax-m1-80kOpen1M$0.55$2.20ReasoningTools paddleocr-vl16K$0.02$0.02Vision qwen-mt-plusOpen16K$0.25$0.75 qwen3-235b-a22b-fp8Open41K$0.20$0.80Reasoning qwen3-235b-a22b-instruct-2507Open131K$0.09$0.58ToolsJSON qwen3-30b-a3b-fp8Open41K$0.09$0.45Reasoning qwen3-32b-fp8Open41K$0.10$0.45Reasoning qwen3-4b-fp8Open128K$0.03$0.03Reasoning qwen3-8b-fp8Open128K$0.04$0.14Reasoning qwen3-coder-480b-a35b-instructOpen262K$0.30$1.30ToolsJSON qwen3-embedding-0.6bOpen33K$0.07$0.00Embeddings qwen3-embedding-8bOpen33K$0.07$0.00Embeddings qwen3-omni-30b-a3b-instructOpen66K$0.25$0.97VisionToolsAudio qwen3-omni-30b-a3b-thinkingOpen66K$0.25$0.97ReasoningVisionTools qwen3-reranker-8bOpen33K$0.05$0.05 r1v4-lite262K$0.20$0.60VisionToolsJSON

Release timeline

Nov 2025

kimi-k2-thinking

Dec 2025

deepseek-v3.2

Dec 2025

glm-4.6v

Dec 2025

glm-4.7

Dec 2025

minimax-m2.1

Details

CategoryCloud platform

Websitenovita.ai

AuthAPI key

Regions-